Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4653 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6726. Min Range: -5.6726
Max Act: 5.6726. Min Act: -0.1700
Data Index: 1494716 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6726. Min Range: -5.6726
Max Act: 5.3601. Min Act: -0.1700
Data Index: 1087164 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6726. Min Range: -5.6726
Max Act: 5.2663. Min Act: -0.1700
Data Index: 761906 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6726. Min Range: -5.6726
Max Act: 5.2038. Min Act: -0.1700
Data Index: 2262566 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6726. Min Range: -5.6726
Max Act: 5.1726. Min Act: -0.1700
Data Index: 5262149 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6726. Min Range: -5.6726
Max Act: 5.2038. Min Act: -0.1700
Data Index: 8065552 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6726. Min Range: -5.6726
Max Act: 5.1726. Min Act: -0.1700
Data Index: 5100555 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6726. Min Range: -5.6726
Max Act: 5.1413. Min Act: -0.1700
Data Index: 8260426 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6726. Min Range: -5.6726
Max Act: 5.1413. Min Act: -0.1700
Data Index: 4355339 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6726. Min Range: -5.6726
Max Act: 5.1101. Min Act: -0.1700
Data Index: 2410960 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6726. Min Range: -5.6726
Max Act: 5.1101. Min Act: -0.1700
Data Index: 7138542 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6726. Min Range: -5.6726
Max Act: 5.1101. Min Act: -0.1700
Data Index: 8065553 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6726. Min Range: -5.6726
Max Act: 5.0476. Min Act: -0.1700
Data Index: 6746720 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6726. Min Range: -5.6726
Max Act: 5.0788. Min Act: -0.1700
Data Index: 8536540 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6726. Min Range: -5.6726
Max Act: 5.0788. Min Act: -0.1700
Data Index: 2410961 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6726. Min Range: -5.6726
Max Act: 5.0788. Min Act: -0.1700
Data Index: 2410953 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6726. Min Range: -5.6726
Max Act: 5.0788. Min Act: -0.1700
Data Index: 576610 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6726. Min Range: -5.6726
Max Act: 5.0788. Min Act: -0.1700
Data Index: 2321780 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6726. Min Range: -5.6726
Max Act: 5.0788. Min Act: -0.1700
Data Index: 4903516 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6726. Min Range: -5.6726
Max Act: 5.0476. Min Act: -0.1700
Data Index: 7091433 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19